Table of Contents

• Text-Based Information Retrieval Using Exponentiated Gradient DescentRon Papka, James P. Callan, Andrew G. Barto. 3-9 [doi]
• Why did TD-Gammon Work?Jordan B. Pollack, Alan D. Blair. 10-16 [doi]
• Neural Models for Part-Whole HierarchiesMaximilian Riesenhuber, Peter Dayan. 17-26 [doi]
• Temporal Low-Order Statistics of Natural SoundsHagai Attias, Christoph E. Schreiner. 27-33 [doi]
• Reconstructing Stimulus Velocity from Neuronal Responses in Area MTWyeth Bair, James R. Cavanaugh, J. Anthony Movshon. 34-40 [doi]
• 3D Object Recognition: A Model of View-Tuned NeuronsEmanuela Bricolo, Tomaso Poggio, Nikos Logothetis. 41-47 [doi]
• A Hierarchical Model of Visual RivalryPeter Dayan. 48-54 [doi]
• Neural Network Models of Chemotaxis in the Nematode Caenorhabditis ElegansThomas C. Ferrée, Ben A. Marcotte, Shawn R. Lockery. 55-61 [doi]
• Extraction of Temporal Features in the Electrosensory System of Weakly Electric FishFabrizio Gabbiani, Walter Metzner, Ralf Wessel, Christof Koch. 62-68 [doi]
• A Neural Model of Visual Contour IntegrationZhaoping Li. 69-75 [doi]
• Learning Exact Patterns of Quasi-synchronization among Spiking Neurons from Data on Multi-unit RecordingsLaura Martignon, Kathryn B. Laskey, Gustavo Deco, Eilon Vaadia. 76-82 [doi]
• Complex-Cell Responses Derived from Center-Surround Inputs: The Surprising Power of Intradendritic ComputationBartlett W. Mel, Daniel L. Ruderman, Kevin A. Archie. 83-89 [doi]
• Orientation Contrast Sensitivity from Long-range Interactions in Visual CortexKlaus Pawelzik, Udo Ernst, Fred Wolf, Theo Geisel. 90-96 [doi]
• Statistically Efficient Estimations Using Cortical Lateral ConnectionsAlexandre Pouget, Kechen Zhang. 97-103 [doi]
• An Architectural Mechanism for Direction-tuned Cortical Simple Cells: The Role of Mutual InhibitionSilvio P. Sabatini, Fabio Solari, Giacomo M. Bisio. 104-110 [doi]
• Cholinergic Modulation Preserves Spike Timing Under Physiologically Realistic Fluctuating InputAkaysha C. Tang, Andreas M. Bartels, Terrence J. Sejnowski. 111-117 [doi]
• A Model of Recurrent Interactions in Primary Visual CortexEmanuel Todorov, Athanassios Siapas, David Somers. 118-126 [doi]
• Neural Learning in Structured Parameter Spaces - Natural Riemannian GradientShun-ichi Amari. 127-133 [doi]
• For Valid Generalization the Size of the Weights is More Important than the Size of the NetworkPeter L. Bartlett. 134-140 [doi]
• Dynamics of TrainingSiegfried Bös, Manfred Opper. 141-147 [doi]
• Multilayer Neural Networks: One or Two Hidden Layers?G. Brightwell, Claire Kenyon, Hélène Paugam-Moisy. 148-154 [doi]
• Support Vector Regression MachinesHarris Drucker, Christopher J. C. Burges, Linda Kaufman, Alex J. Smola, Vladimir Vapnik. 155-161 [doi]
• Size of Multilayer Networks for Exact Learning: Analytic ApproachAndré Elisseeff, Hélène Paugam-Moisy. 162-168 [doi]
• The Effect of Correlated Input Data on the Dynamics of LearningSøren Halkjær, Ole Winther. 169-175 [doi]
• Practical Confidence and Prediction IntervalsTom Heskes. 176-182 [doi]
• Statistical Mechanics of the Mixture of ExpertsKukjin Kang, Jong-Hoon Oh. 183-189 [doi]
• MLP Can Provably Generalize Much Better than VC-bounds IndicateAdam Kowalczyk, Herman L. Ferrá. 190-196 [doi]
• Radial Basis Function Networks and Complexity Regularization in Function LearningAdam Krzyzak, Tamás Linder. 197-203 [doi]
• An Apobayesian Relative of WinnowNick Littlestone, Chris Mesterharm. 204-210 [doi]
• Noisy Spiking Neurons with Temporal Coding have more Computational Power than Sigmoidal NeuronsWolfgang Maass. 211-217 [doi]
• On the Effect of Analog Noise in Discrete-Time Analog ComputationsWolfgang Maass, Pekka Orponen. 218-224 [doi]
• A Mean Field Algorithm for Bayes Learning in Large Feed-forward Neural NetworksManfred Opper, Ole Winther. 225-231 [doi]
• Removing Noise in On-Line Search using Adaptive Batch SizesGenevieve B. Orr. 232-238 [doi]
• Are Hopfield Networks Faster than Conventional Computers?Ian Parberry, Hung-Li Tseng. 239-245 [doi]
• Hebb Learning of Features based on their Information ContentFerdinand Peper, Hideki Noda. 246-252 [doi]
• The Generalisation Cost of RAMnetsRichard Rohwer, Michal Morciniec. 253-259 [doi]
• Learning with Noise and Regularizers in Multilayer Neural NetworksDavid Saad, Sara A. Solla. 260-266 [doi]
• A Variational Principle for Model-based MorphingLawrence K. Saul, Michael I. Jordan. 267-273 [doi]
• Online Learning from Finite Training Sets: An Analytical Case StudyPeter Sollich, David Barber. 274-280 [doi]
• Support Vector Method for Function Approximation, Regression Estimation and Signal ProcessingVladimir Vapnik, Steven E. Golowich, Alex J. Smola. 281-287 [doi]
• The Learning Dynamcis of a Universal ApproximatorAnsgar H. L. West, David Saad, Ian T. Nabney. 288-294 [doi]
• Computing with Infinite NetworksChristopher K. I. Williams. 295-301 [doi]
• Microscopic Equations in Rough Energy Landscape for Neural NetworksK. Y. Michael Wong. 302-308 [doi]
• Time Series Prediction using Mixtures of ExpertsAssaf J. Zeevi, Ron Meir, Robert J. Adler. 309-318 [doi]
• Genetic Algorithms and Explicit Search StatisticsShumeet Baluja. 319-325 [doi]
• Consistent Classification, Firm and SoftYoram Baram. 326-332 [doi]
• Bayesian Model Comparison by Monte Carlo ChainingDavid Barber, Christopher M. Bishop. 333-339 [doi]
• Gaussian Processes for Bayesian Classification via Hybrid Monte CarloDavid Barber, Christopher K. I. Williams. 340-346 [doi]
• Regression with Input-Dependent Noise: A Bayesian TreatmentChristopher M. Bishop, Cazhaow S. Quazaz. 347-353 [doi]
• GTM: A Principled Alternative to the Self-Organizing MapChristopher M. Bishop, Markus Svensén, Christopher K. I. Williams. 354-360 [doi]
• The CONDENSATION Algorithm - Conditional Density Propagation and Applications to Visual TrackingAndrew Blake, Michael Isard. 361-367 [doi]
• Clustering via Concave MinimizationPaul S. Bradley, Olvi L. Mangasarian, W. Nick Street. 368-374 [doi]
• Improving the Accuracy and Speed of Support Vector MachinesChristopher J. C. Burges, Bernhard Schölkopf. 375-381 [doi]
• Estimating Equivalent Kernels for Neural Networks: A Data Perturbation ApproachA. Neil Burgess. 382-388 [doi]
• Promoting Poor Features to Supervisors: Some Inputs Work Better as OutputsRich Caruana, Virginia R. de Sa. 389-395 [doi]
• Self-Organizing and Adaptive Algorithms for Generalized Eigen-DecompositionChanchal Chatterjee, Vwani P. Roychowdhury. 396-402 [doi]
• Representation and Induction of Finite State Machines using Time-Delay Neural NetworksDaniel S. Clouse, C. Lee Giles, Bill G. Horne, Garrison W. Cottrell. 403-409 [doi]
• 488 Solutions to the XOR ProblemFrans Coetzee, Virginia L. Stonick. 410-416 [doi]
• Minimizing Statistical Bias with QueriesDavid A. Cohn. 417-423 [doi]
• MIMIC: Finding Optima by Estimating Probability DensitiesJeremy S. De Bonet, Charles Lee Isbell Jr., Paul A. Viola. 424-430 [doi]
• On a Modification to the Mean Field EM Algorithm in Factorial LearningA. P. Dunmur, D. M. Titterington. 431-437 [doi]
• Softening Discrete RelaxationAndrew M. Finch, Richard C. Wilson, Edwin R. Hancock. 438-444 [doi]
• Limitations of Self-organizing Maps for Vector Quantization and Multidimensional ScalingArthur Flexer. 445-451 [doi]
• Continuous Sigmoidal Belief Networks Trained using Slice SamplingBrendan J. Frey. 452-458 [doi]
• Adaptively Growing Hierarchical Mixtures of ExpertsJürgen Fritsch, Michael Finke, Alex Waibel. 459-465 [doi]
• Balancing Between Bagging and BumpingTom Heskes. 466-472 [doi]
• LSTM can Solve Hard Long Time Lag ProblemsSepp Hochreiter, Jürgen Schmidhuber. 473-479 [doi]
• One-unit Learning Rules for Independent Component AnalysisAapo Hyvärinen, Erkki Oja. 480-486 [doi]
• Recursive Algorithms for Approximating Probabilities in Graphical ModelsTommi Jaakkola, Michael I. Jordan. 487-493 [doi]
• Combinations of Weak ClassifiersChuanyi Ji, Sheng Ma. 494-500 [doi]
• Hidden Markov Decision TreesMichael I. Jordan, Zoubin Ghahramani, Lawrence K. Saul. 501-507 [doi]
• Unification of Information Maximization and MinimizationRyotaro Kamimura. 508-514 [doi]
• Unsupervised Learning by Convex and Conic CodingDaniel D. Lee, H. Sebastian Seung. 515-521 [doi]
• ARC-LH: A New Adaptive Resampling Algorithm for Improving ANN ClassifiersFriedrich Leisch, Kurt Hornik. 522-528 [doi]
• Bayesian Unsupervised Learning of Higher Order StructureMichael S. Lewicki, Terrence J. Sejnowski. 529-535 [doi]
• Source Separation and Density Estimation by Faithful Equivariant SOMJuan K. Lin, Jack D. Cowan, David G. Grier. 536-542 [doi]
• NeuroScale: Novel Topographic Feature Extraction using RBF NetworksDavid Lowe, Michael E. Tipping. 543-549 [doi]
• Ordered Classes and Incomplete Examples in ClassificationMark Mathieson. 550-556 [doi]
• Triangulation by Continuous EmbeddingMarina Meila, Michael I. Jordan. 557-563 [doi]
• Combining Neural Network Regression Estimates with Regularized Linear WeightsChristopher J. Merz, Michael J. Pazzani. 564-570 [doi]
• A Mixture of Experts Classifier with Learning Based on Both Labelled and Unlabelled DataDavid J. Miller, Hasan S. Uyar. 571-577 [doi]
• Learning Bayesian Belief Networks with Neural Network EstimatorsStefano Monti, Gregory F. Cooper. 578-584 [doi]
• Smoothing Regularizers for Projective Basis Function NetworksJohn E. Moody, Thorsteinn S. Rögnvaldsson. 585-591 [doi]
• Competition Among Networks Improves Committee PerformancePaul W. Munro, Bambang Parmanto. 592-598 [doi]
• Adaptive On-line Learning in Changing EnvironmentsNoboru Murata, Klaus-Robert Müller, Andreas Ziehe, Shun-ichi Amari. 599-605 [doi]
• Using Curvature Information for Fast Stochastic SearchGenevieve B. Orr, Todd K. Leen. 606-612 [doi]
• Maximum Likelihood Blind Source Separation: A Context-Sensitive Generalization of ICABarak A. Pearlmutter, Lucas C. Parra. 613-619 [doi]
• A Convergence Proof for the Softassign Quadratic Assignment AlgorithmAnand Rangarajan, Alan L. Yuille, Steven Gold, Eric Mjolsness. 620-626 [doi]
• Second-order Learning Algorithm with Squared Penalty TermKazumi Saito, Ryohei Nakano. 627-633 [doi]
• Monotonicity HintsJoseph Sill, Yaser S. Abu-Mostafa. 634-640 [doi]
• Training Algorithms for Hidden Markov Models using Entropy Based Distance FunctionsYoram Singer, Manfred K. Warmuth. 641-647 [doi]
• Clustering Sequences with Hidden Markov ModelsPadhraic Smyth. 648-654 [doi]
• Fast Network Pruning and Feature Extraction by using the Unit-OBS AlgorithmAchim Stahlberger, Martin Riedmiller. 655-661 [doi]
• Separating Style and ContentJoshua B. Tenenbaum, William T. Freeman. 662-668 [doi]
• Early Brain DamageVolker Tresp, Ralph Neuneier, Hans-Georg Zimmermann. 669-675 [doi]
• Probabilistic Interpretation of Population CodesRichard S. Zemel, Peter Dayan, Alexandre Pouget. 676-684 [doi]
• VLSI Implementation of Cortical Visual Motion Detection Using an Analog Neural ComputerRalph Etienne-Cummings, Jan Van der Spiegel, Naomi Takahashi, Alyssa B. Apsel, Paul Mueller. 685-691 [doi]
• A Spike Based Learning Neuron in Analog VLSIPhilipp Häfliger, Misha Mahowald, Lloyd Watts. 692-698 [doi]
• An Analog Implementation of the Constant Average Statistics Constraint For Sensor CalibrationJohn G. Harris, Yu-Ming Chiang. 699-705 [doi]
• Analog VLSI Circuits for Attention-Based, Visual TrackingTimothy K. Horiuchi, Tonia G. Morris, Christof Koch, Stephen P. DeWeerth. 706-712 [doi]
• Dynamically Adaptable CMOS Winner-Take-All Neural NetworkKunihiko Iizuka, Masayuki Miyamoto, Hirofumi Matsui. 713-719 [doi]
• An Adaptive WTA using Floating Gate TechnologyW. Fritz Kruger, Paul E. Hasler, Bradley A. Minch, Christof Koch. 720-726 [doi]
• A Micropower Analog VLSI HMM State Decoder for WordspottingJohn Lazzaro, John Wawrzynek, Richard Lippmann. 727-733 [doi]
• Bangs, Clicks, Snaps, Thuds and Whacks: An Architecture for Acoustic Transient ProcessingFernando J. Pineda, Gert Cauwenberghs, R. Timothy Edwards. 734-740 [doi]
• A Silicon Model of Amplitude Modulation Detection in the Auditory BrainstemAndré van Schaik, Eric Fragnière, Eric A. Vittoz. 741-750 [doi]
• Dynamic Features for Visual Speechreading: A Systematic ComparisonMichael S. Gray, Javier R. Movellan, Terrence J. Sejnowski. 751-757 [doi]
• Blind Separation of Delayed and Convolved SourcesTe-Won Lee, Anthony J. Bell, Russell H. Lambert. 758-764 [doi]
• A Constructive RBF Network for Writer AdaptationJohn C. Platt, Nada Matic. 765-771 [doi]
• A New Approach to Hybrid HMM/ANN Speech Recognition using Mutual Information Neural NetworksGerhard Rigoll, Christoph Neukirchen. 772-778 [doi]
• Neural Network Modeling of Speech and Music SignalsAlex Röbel. 779-785 [doi]
• A Constructive Learning Algorithm for Discriminant Tangent ModelsDiego Sona, Alessandro Sperduti, Antonina Starita. 786-792 [doi]
• Dual Kalman Filtering Methods for Nonlinear Prediction, Smoothing and EstimationEric A. Wan, Alex T. Nelson. 793-799 [doi]
• Ensemble Methods for Phoneme ClassificationSteve R. Waterhouse, Gary Cook. 800-806 [doi]
• Effective Training of a Neural Network Character Classifier for Word RecognitionLarry S. Yaeger, Richard F. Lyon, Brandyn J. Webb. 807-816 [doi]
• Viewpoint Invariant Face Recognition using Independent Component Analysis and Attractor NetworksMarian Stewart Bartlett, Terrence J. Sejnowski. 817-823 [doi]
• Learning Temporally Persistent Hierarchical RepresentationsSuzanna Becker. 824-830 [doi]
• Edges are the Independent Components of Natural ScenesAnthony J. Bell, Terrence J. Sejnowski. 831-837 [doi]
• Compositionality, MDL Priors, and Object RecognitionElie Bienenstock, Stuart Geman, Daniel Potter. 838-844 [doi]
• Learning Appearance Based Models: Mixtures of Second Moment ExpertsChristoph Bregler, Jitendra Malik. 845 [doi]
• Spatiotemporal Coupling and Scaling of Natural Images and Human Visual SensitivitiesDawei W. Dong. 859-865 [doi]
• Selective Integration: A Model for Disparity EstimationMichael S. Gray, Alexandre Pouget, Richard S. Zemel, Steven J. Nowlan, Terrence J. Sejnowski. 866-872 [doi]
• ARTEX: A Self-organizing Architecture for Classifying Image RegionsStephen Grossberg, James R. Williamson. 873-879 [doi]
• Contour Organisation with the EM AlgorithmJosé A. F. Leite, Edwin R. Hancock. 880-886 [doi]
• Visual Cortex Circuitry and Orientation TuningTrevor Mundel, Alexander Dimitrov, Jack D. Cowan. 887-893 [doi]
• Representing Face Images for Emotion ClassificationCurtis Padgett, Garrison W. Cottrell. 894-900 [doi]
• Rapid Visual Processing using Spike AsynchronySimon J. Thorpe, Jacques Gautrais. 901-907 [doi]
• Interpreting Images by Propagating Bayesian BeliefsYair Weiss. 908-914 [doi]
• Salient Contour Extraction by Temporal Binding in a Cortically-based NetworkShih-Cheng Yen, Leif H. Finkel. 915-924 [doi]
• An Orientation Selective Neural Network for Pattern Identification in Particle DetectorsHalina Abramowicz, David Horn, Ury Naftaly, Carmit Sahar-Pikielny. 925-931 [doi]
• Adaptive Access Control Applied to Ethernet DataTimothy X. Brown. 932-938 [doi]
• Predicting Lifetimes in Dynamically Allocated MemoryDavid A. Cohn, Satinder P. Singh. 939-945 [doi]
• Multi-Task Learning for Stock SelectionJoumana Ghosn, Yoshua Bengio. 946-952 [doi]
• The Neurothermostat: Predictive Optimal Control of Residential Heating SystemsMichael Mozer, Lucky Vidmar, Robert H. Dodier. 953-959 [doi]
• Sequential Tracking in Pricing Financial Options using Model Based and Neural Network ApproachesMahesan Niranjan. 960-966 [doi]
• A Comparison between Neural Networks and other Statistical Techniques for Modeling the Relationship between Tobacco and Alcohol and CancerTony Plate, Pierre Band, Joel Bert, John Grace. 967-973 [doi]
• Reinforcement Learning for Dynamic Channel Allocation in Cellular Telephone SystemsSatinder P. Singh, Dimitri P. Bertsekas. 974-980 [doi]
• Spectroscopic Detection of Cervical Pre-Cancer through Radial Basis Function NetworksKagan Tumer, Nirmala Ramanujam, Rebecca R. Richards-Kortum, Joydeep Ghosh. 981-987 [doi]
• Interpolating Earth-science Data using RBF Networks and Mixtures of ExpertsErnest Wan, Don Bone. 988-994 [doi]
• Multi-effect Decompositions for Financial Data ModelingLizhong Wu, John E. Moody. 995-1004 [doi]
• Multidimensional Triangulation and Interpolation for Reinforcement LearningScott Davies. 1005-1011 [doi]
• Efficient Nonlinear Control with Actor-Tutor ArchitectureKenji Doya. 1012-1018 [doi]
• Local Bandit Approximation for Optimal Learning ProblemsMichael O. Duff, Andrew G. Barto. 1019-1025 [doi]
• Reinforcement Learning for Mixed Open-loop and Closed-loop ControlEric A. Hansen, Andrew G. Barto, Shlomo Zilberstein. 1026-1032 [doi]
• Multi-Grid Methods for Reinforcement Learning in Controlled Diffusion ProcessesStephan Pareigis. 1033-1039 [doi]
• Learning from DemonstrationStefan Schaal. 1040-1046 [doi]
• Exploiting Model Uncertainty Estimates for Safe Dynamic Control LearningJeff G. Schneider. 1047-1053 [doi]
• Analytical Mean Squared Error Curves in Temporal Difference LearningSatinder P. Singh, Peter Dayan. 1054-1060 [doi]
• Learning Decision Theoretic Utilities through Reinforcement LearningMagnus Stensmo, Terrence J. Sejnowski. 1061-1067 [doi]
• On-line Policy Improvement using Monte-Carlo SearchGerald Tesauro, Gregory R. Galperin. 1068-1074 [doi]
• Analysis of Temporal-Diffference Learning with Function ApproximationJohn N. Tsitsiklis, Benjamin Van Roy. 1075-1081 [doi]
• Approximate Solutions to Optimal Stopping ProblemsJohn N. Tsitsiklis, Benjamin Van Roy. 1082-1088 [doi]